publite/backend
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Added metadata parsing for epub

Browse Source
This commit is contained in:
Dmitriy Shishkov 2021-07-01 21:49:49 +05:00
parent d8529740fd
commit aad879a6ed
No known key found for this signature in database
GPG Key ID: 14358F96FCDD8060
1 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
app/epub.py
View File

@ -15,6 +15,8 @@ async def epub2html(file: SpooledTemporaryFile) -> str:
try:
tokens = await epub_to_tokens(file)
print(tokens["metadata"])
...
# TODO: join tokens to HTML
html_content = ""
@ -35,12 +37,23 @@ async def epub_to_tokens(file: SpooledTemporaryFile) -> dict[str, str]:
Where file content is either plain text for xhtml or base64 encoded data for other formats, prepared for embeding to html
"""
tokens = {"metadata": {"test": "t"}}
tokens = {}
async with aiof.tempfile.NamedTemporaryFile() as tmp:
await tmp.write(file.read())
book = epub.read_epub(tmp.name)
# Adding book metadata to tokens list
metadata = {}
metadata["title"] = convert_list(book.get_metadata("DC", "title"))
metadata["author"] = convert_list(book.get_metadata("DC", "creator"))
tokens["metadata"] = metadata.copy()
# Iterating over Items
for item in book.get_items():
item_type = item.get_type()
@ -64,4 +77,15 @@ async def epub_to_tokens(file: SpooledTemporaryFile) -> dict[str, str]:
tokens[name] = f"data:{media_type};base64,{b64_content}"
if item_type == ebooklib.ITEM_COVER:
tokens["metadata"]["cover"] = name
return tokens
def convert_list(titles_list: list[tuple[str, dict[str, str]]]):
res = []
for title_obj in titles_list:
res.append(title_obj[0])
return "; ".join(res)